Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11190
    Prev
    Next
    INDEX
    Explanations

    words relating to broadcasting, academic research, and medicine.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and conjunctions

    np_token-act-pair-logits · gpt-4o-mini

    news broadcasting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")));
    
    -0.74
    "])
    
    -0.72
    AddTagHelper
    -0.72
     itſelf
    -0.72
     himſelf
    -0.71
    ]));
    
    -0.69
     dieux
    -0.69
    "],
    
    -0.68
    %)$
    -0.67
     prisonniers
    -0.66
    POSITIVE LOGITS
    .
    0.64
     without
    0.59
    ,
    0.59
     since
    0.57
     while
    0.55
     entries
    0.53
    TabIndex
    0.51
     when
    0.49
    例文帳に追加
    0.49
     despite
    0.48
    Activations Density 11.628%

    No Known Activations